Research map / 3D vision / 3D generation
Attention-Based Multi-Modal Fusion Network for Semantic Scene Completion
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add the residual attention mechanism (ablation) | AMFNet · NYUv2 | semantic scene completion avg. IoU: 30.1 -> 33.0 | Helped |
| add the residual attention mechanism (ablation) | AMFNet · SUNCG-RGBD | semantic scene completion avg. IoU: 44.3 -> 47.3 | Helped |
| add the 3D-guidance branch (ablation) | AMFNet · NYUv2 | semantic scene completion avg. IoU: 29.9 -> 33.0 | Helped |
| add the 3D-guidance branch (ablation) | AMFNet · SUNCG-RGBD | semantic scene completion avg. IoU: 45.5 -> 47.3 | Helped |
| remove both the attention mechanism and 3D-guidance branch (ablation) | AMFNet · NYUv2 | semantic scene completion avg. IoU: 33.0 -> 29.4 | Hurt |
| remove both the attention mechanism and 3D-guidance branch (ablation) | AMFNet · SUNCG-RGBD | semantic scene completion avg. IoU: 47.3 -> 42.2 | Hurt |
| replace predicted 2D segmentation with ground-truth 2D segmentation (ablation) | AMFNet · NYUv2 | semantic scene completion avg. IoU: 33.0 -> 34.2 | Helped |
| replace predicted 2D segmentation with ground-truth 2D segmentation (ablation) | AMFNet · SUNCG-RGBD | semantic scene completion avg. IoU: 47.3 -> 49.1 | Helped |
Closest papers by meaning
- Unleashing Network Potentials for Semantic Scene Completion (CVPR 2024 · similarity 0.90)
- Bi-SSC: Geometric-Semantic Bidirectional Fusion for Camera-based 3D Semantic Scene Completion (CVPR 2024 · similarity 0.88)
- Context and Geometry Aware Voxel Transformer for Semantic Scene Completion (NeurIPS 2024 · similarity 0.87)
- Voxel Proposal Network via Multi-Frame Knowledge Distillation for Semantic Scene Completion (NeurIPS 2024 · similarity 0.87)
- GOV-NeSF: Generalizable Open-Vocabulary Neural Semantic Fields (CVPR 2024 · similarity 0.87)
- Memory-Augmented Re-Completion for 3D Semantic Scene Completion (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.